International Journal For Multidisciplinary Research

E-ISSN: 2582-2160   •   Impact Factor: 9.24

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 8, Issue 2 (March-April 2026) Submit your research before last 3 days of April to publish your research paper in the issue of March-April.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 8 Issue 2
March-April 2026

Submit your research paper

Indexing Partners
Academia Advanced Sciences Index Bielefeld Academic Search Engine CiteSeer DRJI Google Scholar Independent Search Engine & Directory Network ISI (International Scientific Indexing) Issuu Mendeley Research Networks
RefSeek ResearcherId - Thomson Reuters ResearchGate Scirus Scribd Semantic Scholar UTeM - Universiti Teknikal Malaysia Melaka Wiki for Call for Papers WorldCat Zenodo

Intelligent Chatbot using Transformer Models

Author(s) Dr. Udayasri Kompalli, Mr. Naveen Muni
Country India
Abstract Conversational AI interfaces powered by large language models (LLMs) have become transformative tools across education, software development, and information access. However, deploying state-of-the-art LLMs in accessible, responsive, and secure web applications remains a challenge for individual developers due to prohibitive infrastructure requirements. This paper presents ChatAI, a full-stack browser-based conversational AI application that addresses these challenges by integrating Meta's LLaMA 3.3-70B Versatile model — a 70-billion-parameter dense Transformer — via the Groq Cloud API into a lightweight Python Streamlit application. Leveraging Groq's dedicated Language Processing Unit (LPU) inference hardware, ChatAI achieves sub-second AI response latency using only three pip-installable packages. The system implements multi-user authentication with SHA-256 cryptographic hashing, a toggleable conversation memory mechanism enabling both few-shot in-context learning and zero-shot stateless inference, a bubble-based chat interface with downloadable history, and a real-time analytics dashboard displaying usage KPIs and custom SVG visualisations. Publicly deployed at https://choudary-ai.streamlit.app, ChatAI demonstrates that a production-quality, secure, and analytically instrumented LLM chatbot can be built entirely at the application layer, serving students, researchers, developers, and non-technical users without any model training, local GPU resources, or complex infrastructure.
Keywords Keywords— Conversational AI, Large Language Models (LLMs), Transformer Architecture, Web-Based Chatbot, Real-Time Inference, Cloud-Based AI, Low-Latency Systems, Application-Layer AI Deployment, Multi-User Authentication, SHA-256 Hashing, In-Context Learning, Zero-Shot Learning, Chat Interface Design, Analytics Dashboard, Human–Computer Interaction, Streamlit, LLaMA 3.3-70B, Groq, Language Processing Unit (LPU).
Field Engineering
Published In Volume 8, Issue 2, March-April 2026
Published On 2026-04-16
View / Download PDF File

Share this



E-ISSN 2582-2160
CrossRef

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads
Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 8 Isu 2Cover Page Vol 8 Isu 1Cover Page Vol 7 Isu 6

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA Open Access

About IJFMR
Fees & Payment
Current Issue
Publication Archive 		Submit Research Paper
Track Submission Status
Publication Guidelines
Publication Ethics
Peer Review & Plagiarism 		Join as a Reviewer
Editors & Reviewers
Reviewer Referral Program
Get Reviewer Membership Certi. 		Website/Journal Policies
Usage Policy
Content Policies
Privacy Policy
Contact Us +91-9687-828-838 editor@ijfmr.com
Powered by Sky Research Publication and Journals